3 papers
cs.LG2026
HI-MeshGraphNets: Efficient and Accurate Mesh-based Physics Learning with Hierarchical Multi-scale Graph Neural Networks
SiHun Lee, Dong-Hyuk Park, Taesoo Bang +1
Machine-learned physical surrogate models have become promising alternatives to mesh-based numerical solvers. Among them, graph neural networks (GNNs) are well suited for represent…
nlin.SI2026
Isochronous and underdamped waveforms of modified Emden oscillators
J. de la Cruz, H. C. Rosu
Bernoulli-type waveforms for modified Emden nonlinear oscillators of arbitrary natural power are obtained through a generalized commutative factorization approach. These oscill…
math-ph2026
Clothoid helices obtained via the Lie-Darboux method
H. C. Rosu, J. de la Cruz, P. Lemus-Basilio
The clothoid helices that have both curvature and torsion directly proportional to the arclength are obtained via the Lie-Darboux method and analyzed in some detail. Shifted counte…